423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-04 20:52:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix Llama lora merge crash

Browse Source 
Former-commit-id: c1e2c4ea45ad210e776a192e05e226b34d764135
This commit is contained in:
marko1616 2024-03-24 02:44:35 +08:00
parent 84c3d509fa
commit c083708433
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/llmtuner/train/tuner.py
View File

@ -64,6 +64,15 @@ def export_model(args: Optional[Dict[str, Any]] = None):
for param in model.parameters(): for param in model.parameters():
param.data = param.data.to(output_dtype) param.data = param.data.to(output_dtype)
# Configuration check and fix
config = model.generation_config
if config.do_sample and (
(config.temperature is not None and config.temperature != 1.0) or
(config.top_p is not None and config.top_p != 1.0) or
(config.typical_p is not None and config.typical_p != 1.0)
):
config.do_sample = False
model.save_pretrained( model.save_pretrained(
save_directory=model_args.export_dir, save_directory=model_args.export_dir,
max_shard_size="{}GB".format(model_args.export_size), max_shard_size="{}GB".format(model_args.export_size),